On-line prediction of ultrasonic elliptical vibration cutting surface roughness of tungsten heavy alloy based on deep le
- PDF / 2,435,826 Bytes
- 11 Pages / 595.276 x 790.866 pts Page_size
- 46 Downloads / 238 Views
On-line prediction of ultrasonic elliptical vibration cutting surface roughness of tungsten heavy alloy based on deep learning Yanan Pan1 · Renke Kang1 · Zhigang Dong1 · Wenhao Du2 · Sen Yin1 · Yan Bao1 Received: 29 May 2020 / Accepted: 12 September 2020 © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract The surface quality of tungsten heavy alloy parts has an important influence on its service performance. The accurate on-line prediction of surface roughness in ultra-precision cutting of tungsten heavy alloy has always been the difficulty of research. In this paper, the ultrasonic elliptical vibration cutting technology is used for ultra-precision machining of tungsten heavy alloy. Based on the idea of deep learning, the surface roughness is discretized, and the fitting problem in surface roughness is transformed into a classification problem. The generalization ability of the prediction model is improved by introducing batch standardization and Dropout. The relationship between the vibration signal and the surface roughness is established. Experimental results show that the model can achieve on-line prediction of cutting surface roughness. The prediction accuracy rate can be improved by more than 10% compared with the direct fitting method. Keywords Tungsten heavy alloy · Ultrasonic elliptical vibration cutting · Surface roughness · Deep learning · Vibration signal
Introduction Tungsten heavy alloy are composed of tungsten as the matrix (with the tungsten content of 85–99%) and low amounts of elements such as Ni, Cu, Fe, Co, Mo, Cr, etc. Depending on the composition of the material, Tungsten heavy alloy are commonly classified into W–Ni–Cu and W–Ni–Fe. Due to the excellent material properties—i.e. high density (16.5–19.0 g/cm3 ), high tensile strength (900–1400 MPa), good corrosion resistance, good anti-oxidation (German et al. 1985) and good ray absorption ability, tungsten heavy alloy have a wide range of industrial applications (Rabin et al. 1989), such as nuclear protection (Zhao et al. 1983), national defense and military (Huang and Fan 2001), electrical instrumentation (Zhang and Kang 1999), pressure casting, medical equipment and so on (Kaufmann and Neu 2007).
B
Yan Bao [email protected]
1
Key Laboratory for Precision and Non-traditional Machining Technology of Ministry of Education, Dalian University of Technology, Dalian, People’s Republic of China
2
Institute of Machinery Manufacturing Technology, China Academy of Engineering Physics, Chengdu, People’s Republic of China
It is well known that high-quality processing surface is critical to the service performance of alloy parts, such as corrosion resistance and wear resistance (Gao 2014). In nuclear protection and precision instruments, Tungsten heavy alloy parts require nanometer-level surface roughness. Ultrasonic elliptical vibration cutting, which was first proposed by Shamoto and Moriwaki (1994), is a kind of processing technology that can obtain high quality surface. Due to the high frequency vibration in
Data Loading...